Abstract. This paper extends the N-person IPD game into a more interesting game in economics, namely, the oligopoly game. Due to its market share dynamics, the oligopoly game is mo...
We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approxima...
Realistic domains for learning possess regularities that make it possible to generalize experience across related states. This paper explores an environment-modeling framework tha...
We consider PAC-learning where the distribution is known to the student. The problem addressed here is characterizing when learnability with respect to distribution D1 implies lea...
: We explore the question: “What can a von Neumann processor borrow from dataflow to make it more suitable for a multiprocessor?’’ Starting with a simple, “RISC-like” ins...